svgapp.ai

Export Image as SVG

vectorize_image

Convert a completed canvas image into a downloadable SVG using SVG App's existing vectorizer and credit billing. Accepts canvasId and optionally revisionId from a generation result. Leaves the canvas's active revision unchanged. Returns a pending generationId and a stable assetUrl immediately; poll get_generation_status until completed, then download assetUrl as SVG. Each call starts a new billed vectorization; use status polling instead of calling this tool again.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "canvasId": "<canvasId>"
    },
    "name": "vectorize_image"
  }
}

Input Schema

Name	Required	Description
`canvasId`	Yes	Canvas id returned by an image generation tool.
`workspace`	No	Optional workspace id or slug from list_workspaces. Defaults to the user's personal workspace. Use the same workspace for every call in a workflow, because generations, mascots, and palettes belong to one workspace.
`revisionId`	No	Optional source revision; defaults to the canvas's current revision.

Output Schema

Name	Required	Description	Default
`status`	Yes
`assetUrl`	Yes
`canvasId`	Yes
`mimeType`	Yes
`nextAction`	Yes
`revisionId`	Yes
`generationId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: it discloses credit billing per call, that each call starts a new non-idempotent vectorization (consistent with idempotentHint=false), that the canvas's active revision is left unchanged, and that the tool returns immediately with a pending generationId plus a stable assetUrl. The async contract and cost implications are exactly what annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five short sentences, front-loaded with the action and followed by the async return contract and cost warning, in a logical order. Minor redundancy: 'Accepts canvasId and optionally revisionId' largely repeats the schema, though it usefully ties them to a generation result.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an async, billed mutation with an output schema, the description supplies everything an agent needs: input provenance, side effects, the polling loop, the download step, and the warning not to re-invoke. Return-value details are correctly deferred to the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters are already documented, including the workspace consistency rule and revisionId defaulting. The description restates that canvasId/revisionId come from a generation result but adds no format, constraints, or edge cases beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('convert a completed canvas image into a downloadable SVG') and names the underlying mechanism (SVG App's vectorizer). It is clearly distinguishable from siblings like get_generated_asset (download) and get_generation_status (polling), which it explicitly references.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit prerequisite ('completed canvas image'), the correct follow-up workflow ('poll get_generation_status until completed, then download assetUrl'), and an explicit when-not ('use status polling instead of calling this tool again'). Alternatives are named rather than implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All svgapp.ai tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.